Self-supervised learning

Last updated

Contents

Self-supervised learning (SSL) is a paradigm in machine learning where a model is trained on a task using the data itself to generate supervisory signals, rather than relying on externally-provided labels. In the context of neural networks, self-supervised learning aims to leverage inherent structures or relationships within the input data to create meaningful training signals. SSL tasks are designed so that solving them requires capturing essential features or relationships in the data. The input data is typically augmented or transformed in a way that creates pairs of related samples, where one sample serves as the input, and the other is used to formulate the supervisory signal. This augmentation can involve introducing noise, cropping, rotation, or other transformations. Self-supervised learning more closely imitates the way humans learn to classify objects. [1]

During SSL, the model learns in two steps. First, the task is solved based on an auxiliary or pretext classification task using pseudo-labels, which help to initialize the model parameters. [2] [3] Next, the actual task is performed with supervised or unsupervised learning. [4] [5] [6]

Self-supervised learning has produced promising results in recent years, and has found practical application in fields such as audio processing, and is being used by Facebook and others for speech recognition. [7]

Types

Autoassociative self-supervised learning

Autoassociative self-supervised learning is a specific category of self-supervised learning where a neural network is trained to reproduce or reconstruct its own input data. [8] In other words, the model is tasked with learning a representation of the data that captures its essential features or structure, allowing it to regenerate the original input.

The term "autoassociative" comes from the fact that the model is essentially associating the input data with itself. This is often achieved using autoencoders, which are a type of neural network architecture used for representation learning. Autoencoders consist of an encoder network that maps the input data to a lower-dimensional representation (latent space), and a decoder network that reconstructs the input from this representation.

The training process involves presenting the model with input data and requiring it to reconstruct the same data as closely as possible. The loss function used during training typically penalizes the difference between the original input and the reconstructed output (e.g. mean squared error). By minimizing this reconstruction error, the autoencoder learns a meaningful representation of the data in its latent space.

Contrastive self-supervised learning

For a binary classification task, training data can be divided into positive examples and negative examples. Positive examples are those that match the target. For example, if training a classifier to identify birds, the positive training data would include images that contain birds. Negative examples would be images that do not. [9] Contrastive self-supervised learning uses both positive and negative examples. The loss function in contrastive learning is used to minimize the distance between positive sample pairs, while maximizing the distance between negative sample pairs. [9]

An early example uses a pair of 1-dimensional convolutional neural networks to process a pair of images and maximize their agreement. [10]

Contrastive Language-Image Pre-training (CLIP) allows joint pretraining of a text encoder and an image encoder, such that a matching image-text pair have image encoding vector and text encoding vector that span a small angle (having a large cosine similarity).

InfoNCE (Noise-Contrastive Estimation) [11] is a method to optimize two models jointly, based on Noise Contrastive Estimation (NCE). [12] Given a set of random samples containing one positive sample from and negative samples from the 'proposal' distribution , it minimizes the following loss function:

Non-contrastive self-supervised learning

Non-contrastive self-supervised learning (NCSSL) uses only positive examples. Counterintuitively, NCSSL converges on a useful local minimum rather than reaching a trivial solution, with zero loss. For the example of binary classification, it would trivially learn to classify each example as positive. Effective NCSSL requires an extra predictor on the online side that does not back-propagate on the target side. [9]

Comparison with other forms of machine learning

SSL belongs to supervised learning methods insofar as the goal is to generate a classified output from the input. At the same time, however, it does not require the explicit use of labeled input-output pairs. Instead, correlations, metadata embedded in the data, or domain knowledge present in the input are implicitly and autonomously extracted from the data. These supervisory signals, generated from the data, can then be used for training. [1]

SSL is similar to unsupervised learning in that it does not require labels in the sample data. Unlike unsupervised learning, however, learning is not done using inherent data structures.

Semi-supervised learning combines supervised and unsupervised learning, requiring only a small portion of the learning data be labeled. [3]

In transfer learning a model designed for one task is reused on a different task. [13]

Training an autoencoder intrinsically constitutes a self-supervised process, because the output pattern needs to become an optimal reconstruction of the input pattern itself. However, in current jargon, the term 'self-supervised' has become associated with classification tasks that are based on a pretext-task training setup. This involves the (human) design of such pretext task(s), unlike the case of fully self-contained autoencoder training. [8]

In reinforcement learning, self-supervising learning from a combination of losses can create abstract representations where only the most important information about the state are kept in a compressed way. [14]

Examples

Self-supervised learning is particularly suitable for speech recognition. For example, Facebook developed wav2vec, a self-supervised algorithm, to perform speech recognition using two deep convolutional neural networks that build on each other. [7]

Google's Bidirectional Encoder Representations from Transformers (BERT) model is used to better understand the context of search queries. [15]

OpenAI's GPT-3 is an autoregressive language model that can be used in language processing. It can be used to translate texts or answer questions, among other things. [16]

Bootstrap Your Own Latent (BYOL) is a NCSSL that produced excellent results on ImageNet and on transfer and semi-supervised benchmarks. [17]

The Yarowsky algorithm is an example of self-supervised learning in natural language processing. From a small number of labeled examples, it learns to predict which word sense of a polysemous word is being used at a given point in text.

DirectPred is a NCSSL that directly sets the predictor weights instead of learning it via typical gradient descent. [9]

Self-GenomeNet is an example of self-supervised learning in genomics. [18]

Related Research Articles

<span class="mw-page-title-main">Neural network (machine learning)</span> Computational model used in machine learning, based on connected, hierarchical functions

In machine learning, a neural network is a model inspired by the structure and function of biological neural networks in animal brains.

Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without explicit instructions. Advances in the field of deep learning have allowed neural networks to surpass many previous approaches in performance.

Unsupervised learning is a framework in machine learning where, in contrast to supervised learning, algorithms learn patterns exclusively from unlabeled data. Other frameworks in the spectrum of supervisions include weak- or semi-supervision, where a small portion of the data is tagged, and self-supervision. Some researchers consider self-supervised learning a form of unsupervised learning.

<span class="mw-page-title-main">Autoencoder</span> Neural network that learns efficient data encoding in an unsupervised manner

An autoencoder is a type of artificial neural network used to learn efficient codings of unlabeled data. An autoencoder learns two functions: an encoding function that transforms the input data, and a decoding function that recreates the input data from the encoded representation. The autoencoder learns an efficient representation (encoding) for a set of data, typically for dimensionality reduction, to generate lower-dimensional embeddings for subsequent use by other machine learning algorithms.

<span class="mw-page-title-main">Spiking neural network</span> Artificial neural network that mimics neurons

Spiking neural networks (SNNs) are artificial neural networks (ANN) that more closely mimic natural neural networks. These models leverage timing of discrete spikes as the main information carrier.

There are many types of artificial neural networks (ANN).

<span class="mw-page-title-main">Deep learning</span> Branch of machine learning

Deep learning is a subset of machine learning that focuses on utilizing neural networks to perform tasks such as classification, regression, and representation learning. The field takes inspiration from biological neuroscience and is centered around stacking artificial neurons into layers and "training" them to process data. The adjective "deep" refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

<span class="mw-page-title-main">Feature learning</span> Set of learning techniques in machine learning

In machine learning (ML), feature learning or representation learning is a set of techniques that allow a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task.

A convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns features by itself via filter optimization. This type of deep learning network has been applied to process and make predictions from many different types of data including text, images and audio. Convolution-based networks are the de-facto standard in deep learning-based approaches to computer vision and image processing, and have only recently have been replaced -- in some cases -- by newer deep learning architectures such as the transformer. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer, 10,000 weights would be required for processing an image sized 100 × 100 pixels. However, applying cascaded convolution kernels, only 25 neurons are required to process 5x5-sized tiles. Higher-layer features are extracted from wider context windows, compared to lower-layer features.

A recursive neural network is a kind of deep neural network created by applying the same set of weights recursively over a structured input, to produce a structured prediction over variable-size input structures, or a scalar prediction on it, by traversing a given structure in topological order. These networks were first introduced to learn distributed representations of structure, but have been successful in multiple applications, for instance in learning sequence and tree structures in natural language processing.

<span class="mw-page-title-main">Quantum machine learning</span> Interdisciplinary research area at the intersection of quantum physics and machine learning

Quantum machine learning is the integration of quantum algorithms within machine learning programs.

<span class="mw-page-title-main">Domain adaptation</span> Field associated with machine learning and transfer learning

Domain adaptation is a field associated with machine learning and transfer learning. This scenario arises when we aim at learning a model from a source data distribution and applying that model on a different target data distribution. For instance, one of the tasks of the common spam filtering problem consists in adapting a model from one user to a new user who receives significantly different emails. Domain adaptation has also been shown to be beneficial to learning unrelated sources. When more than one source distribution is available, the problem is referred to as multi-source domain adaptation.

<span class="mw-page-title-main">Generative adversarial network</span> Deep learning method

A generative adversarial network (GAN) is a class of machine learning frameworks and a prominent framework for approaching generative artificial intelligence. The concept was initially developed by Ian Goodfellow and his colleagues in June 2014. In a GAN, two neural networks contest with each other in the form of a zero-sum game, where one agent's gain is another agent's loss.

WaveNet is a deep neural network for generating raw audio. It was created by researchers at London-based AI firm DeepMind. The technique, outlined in a paper in September 2016, is able to generate relatively realistic-sounding human-like voices by directly modelling waveforms using a neural network method trained with recordings of real speech. Tests with US English and Mandarin reportedly showed that the system outperforms Google's best existing text-to-speech (TTS) systems, although as of 2016 its text-to-speech synthesis still was less convincing than actual human speech. WaveNet's ability to generate raw waveforms means that it can model any kind of audio, including music.

Paraphrase or paraphrasing in computational linguistics is the natural language processing task of detecting and generating paraphrases. Applications of paraphrasing are varied including information retrieval, question answering, text summarization, and plagiarism detection. Paraphrasing is also useful in the evaluation of machine translation, as well as semantic parsing and generation of new samples to expand existing corpora.

<span class="mw-page-title-main">Variational autoencoder</span> Deep learning generative model to encode data representation

In machine learning, a variational autoencoder (VAE) is an artificial neural network architecture introduced by Diederik P. Kingma and Max Welling. It is part of the families of probabilistic graphical models and variational Bayesian methods.

A latent space, also known as a latent feature space or embedding space, is an embedding of a set of items within a manifold in which items resembling each other are positioned closer to one another. Position within the latent space can be viewed as being defined by a set of latent variables that emerge from the resemblances from the objects.

An energy-based model (EBM) is an application of canonical ensemble formulation from statistical physics for learning from data. The approach prominently appears in generative artificial intelligence.

Emotion recognition in conversation (ERC) is a sub-field of emotion recognition, that focuses on mining human emotions from conversations or dialogues having two or more interlocutors. The datasets in this field are usually derived from social platforms that allow free and plenty of samples, often containing multimodal data. Self- and inter-personal influences play critical role in identifying some basic emotions, such as, fear, anger, joy, surprise, etc. The more fine grained the emotion labels are the harder it is to detect the correct emotion. ERC poses a number of challenges, such as, conversational-context modeling, speaker-state modeling, presence of sarcasm in conversation, emotion shift across consecutive utterances of the same interlocutor.

<span class="mw-page-title-main">Vision transformer</span> Machine learning model for vision processing

A vision transformer (ViT) is a transformer designed for computer vision. A ViT decomposes an input image into a series of patches, serializes each patch into a vector, and maps it to a smaller dimension with a single matrix multiplication. These vector embeddings are then processed by a transformer encoder as if they were token embeddings.

References

  1. 1 2 Bouchard, Louis (25 November 2020). "What is Self-Supervised Learning? | Will machines ever be able to learn like humans?". Medium. Retrieved 9 June 2021.
  2. ↑ Doersch, Carl; Zisserman, Andrew (October 2017). "Multi-task Self-Supervised Visual Learning". 2017 IEEE International Conference on Computer Vision (ICCV). IEEE. pp. 2070–2079. arXiv: 1708.07860 . doi:10.1109/iccv.2017.226. ISBN   978-1-5386-1032-9. S2CID   473729.
  3. 1 2 Beyer, Lucas; Zhai, Xiaohua; Oliver, Avital; Kolesnikov, Alexander (October 2019). "S4L: Self-Supervised Semi-Supervised Learning". 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE. pp. 1476–1485. arXiv: 1905.03670 . doi:10.1109/iccv.2019.00156. ISBN   978-1-7281-4803-8. S2CID   167209887.
  4. ↑ Doersch, Carl; Gupta, Abhinav; Efros, Alexei A. (December 2015). "Unsupervised Visual Representation Learning by Context Prediction". 2015 IEEE International Conference on Computer Vision (ICCV). IEEE. pp. 1422–1430. arXiv: 1505.05192 . doi:10.1109/iccv.2015.167. ISBN   978-1-4673-8391-2. S2CID   9062671.
  5. ↑ Zheng, Xin; Wang, Yong; Wang, Guoyou; Liu, Jianguo (April 2018). "Fast and robust segmentation of white blood cell images by self-supervised learning". Micron. 107: 55–71. doi:10.1016/j.micron.2018.01.010. ISSN   0968-4328. PMID   29425969. S2CID   3796689.
  6. ↑ Gidaris, Spyros; Bursuc, Andrei; Komodakis, Nikos; Perez, Patrick Perez; Cord, Matthieu (October 2019). "Boosting Few-Shot Visual Learning with Self-Supervision". 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE. pp. 8058–8067. arXiv: 1906.05186 . doi:10.1109/iccv.2019.00815. ISBN   978-1-7281-4803-8. S2CID   186206588.
  7. 1 2 "Wav2vec: State-of-the-art speech recognition through self-supervision". ai.facebook.com. Retrieved 9 June 2021.
  8. 1 2 Kramer, Mark A. (1991). "Nonlinear principal component analysis using autoassociative neural networks" (PDF). AIChE Journal. 37 (2): 233–243. Bibcode:1991AIChE..37..233K. doi:10.1002/aic.690370209.
  9. 1 2 3 4 "Demystifying a key self-supervised learning technique: Non-contrastive learning". ai.facebook.com. Retrieved 5 October 2021.
  10. ↑ Becker, Suzanna; Hinton, Geoffrey E. (January 1992). "Self-organizing neural network that discovers surfaces in random-dot stereograms". Nature. 355 (6356): 161–163. Bibcode:1992Natur.355..161B. doi:10.1038/355161a0. ISSN   1476-4687. PMID   1729650.
  11. ↑ Oord, Aaron van den; Li, Yazhe; Vinyals, Oriol (22 January 2019), Representation Learning with Contrastive Predictive Coding, arXiv: 1807.03748
  12. ↑ Gutmann, Michael; Hyvärinen, Aapo (31 March 2010). "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models". Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings: 297–304.
  13. ↑ Littwin, Etai; Wolf, Lior (June 2016). "The Multiverse Loss for Robust Transfer Learning". 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. pp. 3957–3966. arXiv: 1511.09033 . doi:10.1109/cvpr.2016.429. ISBN   978-1-4673-8851-1. S2CID   6517610.
  14. ↑ Francois-Lavet, Vincent; Bengio, Yoshua; Precup, Doina; Pineau, Joelle (2019). "Combined Reinforcement Learning via Abstract Representations". Proceedings of the AAAI Conference on Artificial Intelligence. arXiv: 1809.04506 .
  15. ↑ "Open Sourcing BERT: State-of-the-Art Pre-training for Natural Language Processing". Google AI Blog. 2 November 2018. Retrieved 9 June 2021.
  16. ↑ Wilcox, Ethan; Qian, Peng; Futrell, Richard; Kohita, Ryosuke; Levy, Roger; Ballesteros, Miguel (2020). "Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models". Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg, PA, USA: Association for Computational Linguistics. pp. 4640–4652. arXiv: 2010.05725 . doi:10.18653/v1/2020.emnlp-main.375. S2CID   222291675.
  17. ↑ Grill, Jean-Bastien; Strub, Florian; Altché, Florent; Tallec, Corentin; Richemond, Pierre H.; Buchatskaya, Elena; Doersch, Carl; Pires, Bernardo Avila; Guo, Zhaohan Daniel; Azar, Mohammad Gheshlaghi; Piot, Bilal (10 September 2020). "Bootstrap your own latent: A new approach to self-supervised Learning". arXiv: 2006.07733 [cs.LG].
  18. ↑ Gündüz, Hüseyin Anil; Binder, Martin; To, Xiao-Yin; Mreches, René; Bischl, Bernd; McHardy, Alice C.; Münch, Philipp C.; Rezaei, Mina (11 September 2023). "A self-supervised deep learning method for data-efficient training in genomics". Communications Biology. 6 (1): 928. doi: 10.1038/s42003-023-05310-2 . ISSN   2399-3642. PMC   10495322 . PMID   37696966.

Further reading

This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.